Model save

README.md

@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 # mistral-sft-lora-fsdp
 
 This model is a fine-tuned version of [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0178
 
 ## Model description
 
@@ -51,7 +53,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 1    | 1.8099          |
+| 0.9809        | 1.0   | 20   | 1.0178          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "q_proj",
-    "gate_proj",
     "v_proj",
     "o_proj",
-    "down_proj"
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e7c70b69f5bfd1902d13f38ebf24e6dbe1c5233de6df1a2d214c2a7b782e24
+oid sha256:3af779e366c638a194f86a7c739fa2410c3b76dd8c4205710484d9f4b88d3599
 size 414337624

runs/Jan04_17-38-23_gpu-server/events.out.tfevents.1736012482.gpu-server.1862567.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1c5dc6118a7a9abe49a44a217baaabaa153b52e19d0b26032ada60ed197032
-size 6470
+oid sha256:57295ff647b5d41c062a3de66762749f9ff2a408eb27fa102652dcba0ba2d7c1
+size 7084